curl --request POST \
--url https://api.modellix.ai/api/v1/alibaba/wan2.7-image-edit/async \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"images": [
"https://example.com/photo.jpg"
],
"prompt": "Transform this photo into a watercolor painting style"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}Wan 2.7 Image Edit is the standard image editing model with faster generation speed. Supports multi-image reference, interactive editing, sequential generation, and custom color themes. Max 2K output. Does not support 4K.
curl --request POST \
--url https://api.modellix.ai/api/v1/alibaba/wan2.7-image-edit/async \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"images": [
"https://example.com/photo.jpg"
],
"prompt": "Transform this photo into a watercolor painting style"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}Documentation Index
Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Input image URLs or Base64 strings (1-9 images). Formats: JPEG, JPG, PNG, BMP, WEBP. Resolution: [240, 8000] px per side, aspect ratio [1:8, 8:1], max 20MB per image
1 - 9 elements["https://example.com/image1.jpg"]Image editing instruction, supports Chinese and English
1 - 5000"Apply the graffiti from image 2 onto the car in image 1"
Output resolution. Preset: 1K, 2K. Or custom pixels (format: widthheight, range [768768, 2048*2048]). Max 2K for image editing
"2K"
Number of images. Default mode (enable_sequential=false): 1-4, default 4. Sequential mode (enable_sequential=true): 1-12, default 12. Directly affects cost
1 <= x <= 121
Random seed for reproducible results
0 <= x <= 2147483647Enable sequential mode for generating coherent multi-image sets from image input